AI Security Engineer – Researcher

Intellectsoft

. Design and build core agent harnesses covering function calling, tool interfaces, context assembly, retrieval integration, subagent delegation, retry logic, and failure handling .

Posted 10/28/2026full-timeBengaluru • IndiaMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates strong Python development skills for building research-grade tooling and automated reporting pipelines, alongside hands-on expertise in AI attack surfaces and application security. Capable of translating client requirements into robust agent architectures while effectively communicating technical trade-offs to stakeholders.

Highest-signal resume keywords

Python DevelopmentApplication SecurityVulnerability AnalysisMachine Learning SecurityAgentic Architectures

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Security ResearchDetection EngineeringThreat ModelingAdversarial MLStatistical Experiment DesignEvaluation MetricsFailure Mode AnalysisTool CallingPrompt InjectionPolicy-as-Code

Soft Skills

Stakeholder CommunicationTechnical Trade-off Articulation

Tools & Technologies

PyTorchTensorFlowHugging Face TransformersLangChainDockerKubernetesAWSAzureGCPBurp Suite

Industry Keywords

LLM AppsMCP EcosystemsISO 42001NIST AI RMFEU AI ActMITRE ATLASOWASP LLM & ASI Top 10Red-TeamingDefensive EngineeringCVE Disclosures

Tech Stack

Tools & technologies

AssemblyAWSAzureDockerGoogle Cloud PlatformKubernetesPythonPyTorchSDLCTensorflowTerraform

About the role

Key responsibilities & impact

Design and build core agent harnesses covering function calling, tool interfaces, context assembly, retrieval integration, subagent delegation, retry logic, and failure handling
Take agentic systems from initial concept to scalable production, managing deployment, monitoring, cost, latency, and operational support against live enterprise client data
Build and maintain rigorous evaluation suites, task benchmarks, scoring rubrics, and regression tests using Langfuse, Pydantic Logfire, or custom SDKs
Integrate client enterprise systems, data sources, and internal APIs as accessible agent tools, including building and managing MCP servers
Translate ambiguous client requirements into robust agent architectures and advise stakeholders on whether an agentic pattern is appropriate
Interface directly with client stakeholders and articulate technical trade-offs clearly to non-technical audiences
Contribute reusable harness components to shared internal tooling and document design decisions for audit, validation, and handover standards

Requirements

What you’ll need

3+ years in security research, offensive security, ML/AI security, detection engineering, or a related discipline
Strong Python development skills for building research-grade tooling, async services, CLIs, SDKs, and automated reporting pipelines
Strong foundations in application security, threat modeling, and failure modes specific to autonomous and transformer-based systems
Hands-on expertise in at least one major AI attack surface: LLM apps, agentic/tool-using workflows, or ML training/inference pipelines
Demonstrated experience in vulnerability analysis, detection engineering, adversarial ML, policy-as-code/authorization, red-teaming, or secure SDLC practices
Solid grasp of LLMs, retrieval-augmented generation (RAG), prompt injection, and tool calling
Ability to design experiments with held-out evaluations and statistically rigorous metrics
Ability to distinguish exploitable vulnerabilities from theoretical edge cases, eliminate evaluation test leakage, and verify genuine generalization
Capacity to evaluate cutting-edge security literature, advisories, and CVE disclosures and convert them into operational exploits and defensive mechanisms
Working familiarity with Python, PyTorch/TensorFlow, Hugging Face Transformers
Working familiarity with LangChain, LangGraph, LlamaIndex, MCP, OpenAI/Anthropic SDKs
Working familiarity with Garak, PyRIT, promptfoo, Giskard, ART, NeMo Guardrails, Guardrails AI, LLM Guard, Rebuff
Working familiarity with Burp Suite, OWASP ZAP, Semgrep, Nuclei, ModelScan, picklescan
Working familiarity with OPA/Cedar, Docker, Kubernetes, Terraform, AWS/Azure/GCP, OpenTelemetry, LangSmith, Langfuse
Nice-to-have: dual experience spanning offensive red-teaming and defensive engineering
Nice-to-have: practical experience with agentic architectures, MCP ecosystems, and multi-agent frameworks
Nice-to-have: applied knowledge of NIST AI RMF, ISO 42001, EU AI Act, MITRE ATLAS, OWASP LLM & ASI Top 10
Nice-to-have: experience implementing policy-as-code, applied cryptography, or CI/CD security quality gates
Nice-to-have: proven track record in cross-framework, cross-dataset, or real-world validation of security controls
Nice-to-have: published security research, CVE disclosures, security advisories, or competitive CTF/red-teaming accomplishments

Benefits

Comp & perks

Employment-based cooperation
Comprehensive insurance for you and your family (health, life, and accident)
Paid PTO policy (vacation, sick leaves, and public holidays)
Tech equipment provided
Udemy courses, workshops, trainings & expert knowledge-sharing
Flexible hours & work setup